Add crime per 1k people

pipeline/download/lsoa_population.py

@@ -0,0 +1,71 @@
+"""Download Census 2021 usual resident population by LSOA.
+
+Source: NOMIS (ONS Census 2021 — TS001 dataset)
+License: Open Government Licence v3.0
+"""
+
+import argparse
+from io import BytesIO
+from pathlib import Path
+
+import httpx
+import polars as pl
+
+# NOMIS API: Census 2021 TS001 (usual residents) by LSOA 2021 (TYPE151)
+# c2021_restype_3=0 selects "Total: All usual residents"
+# NOMIS paginates at 25,000 rows by default, so we paginate with recordoffset.
+BASE_URL = "https://www.nomisweb.co.uk/api/v01/dataset/NM_2021_1.data.csv?date=latest&geography=TYPE151&measures=20100&c2021_restype_3=0&select=GEOGRAPHY_CODE,OBS_VALUE"
+PAGE_SIZE = 25000
+
+
+def download_and_convert(output_path: Path) -> None:
+    print("Downloading Census 2021 LSOA population from NOMIS...")
+    frames = []
+    offset = 0
+    while True:
+        url = f"{BASE_URL}&recordoffset={offset}"
+        response = httpx.get(url, follow_redirects=True, timeout=120)
+        response.raise_for_status()
+        if len(response.content) == 0:
+            break
+        chunk = pl.read_csv(BytesIO(response.content))
+        if chunk.height == 0:
+            break
+        frames.append(chunk)
+        print(f"  Fetched {chunk.height} rows (offset={offset})")
+        if chunk.height < PAGE_SIZE:
+            break
+        offset += PAGE_SIZE
+
+    df = pl.concat(frames)
+    print(f"Total rows: {df.height}")
+
+    result = df.rename({"GEOGRAPHY_CODE": "lsoa21", "OBS_VALUE": "population"}).with_columns(
+        pl.col("population").cast(pl.UInt32),
+    )
+
+    # Filter to England only (E prefix)
+    result = result.filter(pl.col("lsoa21").str.starts_with("E"))
+
+    print(f"England LSOAs: {result.height}")
+    print(f"Population range: {result['population'].min()} - {result['population'].max()}")
+    print(f"Mean population: {result['population'].mean():.0f}")
+
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+    result.write_parquet(output_path, compression="zstd")
+    print(f"Saved to {output_path}")
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Download Census 2021 population by LSOA"
+    )
+    parser.add_argument(
+        "--output", type=Path, required=True, help="Output parquet file path"
+    )
+    args = parser.parse_args()
+    download_and_convert(args.output)
+
+
+if __name__ == "__main__":
+    main()

pipeline/transform/merge.py

@@ -43,6 +43,8 @@ _AREA_COLUMNS = [
     "Other crime (avg/yr)",
     "Serious crime (avg/yr)",
     "Minor crime (avg/yr)",
+    "Serious crime per 1k residents (avg/yr)",
+    "Minor crime per 1k residents (avg/yr)",
     # Amenities
     "Number of restaurants within 2km",
     "Number of grocery shops and supermarkets within 2km",
@@ -77,6 +79,7 @@ def _build(
     broadband_path: Path,
     geosure_path: Path,
     rental_prices_path: Path,
+    lsoa_population_path: Path,
 ) -> tuple[pl.DataFrame, pl.DataFrame]:
     """Build postcode and properties dataframes from epc_pp + auxiliary data.
 
@@ -171,6 +174,17 @@ def _build(
         ).alias("minor_crime_avg_yr"),
     )
 
+    lsoa_pop = pl.scan_parquet(lsoa_population_path)
+    wide = wide.join(lsoa_pop, on="lsoa21", how="left")
+    wide = wide.with_columns(
+        (pl.col("serious_crime_avg_yr") / pl.col("population") * 1000)
+        .round(1)
+        .alias("serious_crime_per_1k"),
+        (pl.col("minor_crime_avg_yr") / pl.col("population") * 1000)
+        .round(1)
+        .alias("minor_crime_per_1k"),
+    ).drop("population")
+
     poi_counts = pl.scan_parquet(poi_proximity_path)
     wide = wide.join(poi_counts, on="postcode", how="left")
 
@@ -301,6 +315,8 @@ def _build(
                 "max_download_speed": "Max available download speed (Mbps)",
                 "serious_crime_avg_yr": "Serious crime (avg/yr)",
                 "minor_crime_avg_yr": "Minor crime (avg/yr)",
+                "serious_crime_per_1k": "Serious crime per 1k residents (avg/yr)",
+                "minor_crime_per_1k": "Minor crime per 1k residents (avg/yr)",
                 "environmental_risk": "Environmental risk",
                 "collapsible_deposits_risk": "Collapsible deposits risk",
                 "compressible_ground_risk": "Compressible ground risk",
@@ -389,6 +405,12 @@ def main():
         required=True,
         help="ONS rental prices by LA and bedroom count parquet file",
     )
+    parser.add_argument(
+        "--lsoa-population",
+        type=Path,
+        required=True,
+        help="Census 2021 population by LSOA parquet file",
+    )
     parser.add_argument(
         "--output-postcodes", type=Path, required=True, help="Output postcode parquet file path"
     )
@@ -409,6 +431,7 @@ def main():
         broadband_path=args.broadband,
         geosure_path=args.geosure,
         rental_prices_path=args.rental_prices,
+        lsoa_population_path=args.lsoa_population,
     )
 
     print(f"\nPostcode columns: {postcode_df.columns}")